Automatic annotation is an elegant alternative to explicit recognition in images. In annotation, the image is matched with keyword models, and the most relevant keywords are assig...
We introduce the notion of co-saliency for image matching. Our matching algorithm combines the discriminative power of feature correspondences with the descriptive power of matchi...
Subspace learning techniques are widespread in pattern recognition research. They include PCA, ICA, LPP, etc. These techniques are generally linear and unsupervised. The problem o...
In this paper, we present a novel solution to the image annotation problem which annotates images using search and data mining technologies. An accurate keyword is required to ini...
Smoothing of biomedical images should preserve gray-level transitions between adjacent tissues, while restoring contours consistent with anatomical structures. Anisotropic diffusi...